Improvised Software Code Comprehension Using Data Mining

Millions of lines of code are used to create the modern software applications, which are more complicated in terms of their structure, behaviour, and functionality. The rapid advancement of supporting and enabling technologies, for example, is one reason why the development life cycles of these applications show a propensity to get shorter. As a result, a growing amount of the expense associated with software development moves from the generation of new artefacts to their adaption. Understanding the layout, functionality, and behaviour of current code artefacts is essential to this activity. The task of understanding code is crucial to software maintenance. We employed data mining techniques including clustering, classification, and associative rules to improvise software code comprehension .